Comparison of Machine Learning Approaches for Classifying Spinodal Events

TL;DR

This paper compares various deep learning models and ensemble methods for classifying spinodal events, finding that NAT and MobileViT outperform traditional CNNs in accuracy, AUC, and F1 score.

Contribution

It evaluates and compares state-of-the-art deep learning models and ensemble approaches on the spinodal dataset, highlighting the superior performance of NAT and MobileViT.

Findings

NAT and MobileViT achieve highest accuracy, AUC, and F1 scores.

Ensemble models like majority voting and AdaBoost are also evaluated.

Deep learning models outperform traditional CNNs in this classification task.

Abstract

In this work, we compare the performance of deep learning models for classifying the spinodal dataset. We evaluate state-of-the-art models (MobileViT, NAT, EfficientNet, CNN), alongside several ensemble models (majority voting, AdaBoost). Additionally, we explore the dataset in a transformed color space. Our findings show that NAT and MobileViT outperform other models, achieving the highest metrics-accuracy, AUC, and F1 score on both training and testing data (NAT: 94.65, 0.98, 0.94; MobileViT: 94.20, 0.98, 0.94), surpassing the earlier CNN model (88.44, 0.95, 0.88). We also discuss failure cases for the top performing models.